Text

PRIN/SPRIN: On Extracting Point-Wise Rotation Invariant Features

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, P oint-wise R otation I nvariant N etwork, focusing on rotation invariant feature extraction in point clouds analysis. We construct spherical signals by Density Aware Adaptive Sampling to deal with distorted point distributions in spherical space. Spherical Voxel Convolution and Point Re-sampling are proposed to extract rotation invariant features for each point. In addition, we extend PRIN to a sparse version called SPRIN, which directly operates on sparse point clouds. Both PRIN and SPRIN can be applied to tasks ranging from object classification, part segmentation, to 3D feature matching and label alignment. Results show that, on the dataset with randomly rotated point clouds, SPRIN demonstrates better performance than state-of-the-art methods without any data augmentation. We also provide thorough theoretical proof and analysis for point-wise rotation invariance achieved by our methods. The code to reproduce our results will be made publicly available.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.12 Part 2 December 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 9489-9502

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

FEATURE LEARNING
ROTATION INVARIANCE
POINT CLOUD
OBJECT ANALYSIS

Info Detail Spesifik

10.1109/TPAMI.2021.3130590

Pernyataan Tanggungjawab

Yang You, Yujing Lou, Ruoxi Shi, Qi Liu, Yu-Wing Tai, et al.

Versi lain/terkait

Lampiran Berkas

Komentar